Human falls are a global public health issue resulting in over 373 million severe injuries and 646,000 deaths yearly Falls result in direct financial cost to health systems and indirectly to society productivity Unsurprisingly, human fall detection and prevention are a major focus of health research In this article, we consider deep learning for fall detection in an IoT and fog computing environment We propose a Convolutional Neural Network composed of three convolutional layers, two maxpool, and three fully-connected layers as our deep learning model We evaluate its performance using three open data sets and against extant research Our approach for resolving dimensionality and modelling simplicity issues is outlined Accuracy, precision, sensitivity, specificity, and the Matthews Correlation Coefficient are used to evaluate performance The best results are achieved when using data augmentation during the training process The paper concludes with a discussion of challenges and future directions for research in this domain

https://www.mdpi.com/1424-8220/19/7/1644/pdf

Accelerometer-Based Human Fall Detection Using Convolutional Neural Networks

Leveraging Deep Learning and IoT big data analytics to support the smart cities development: Review and future directions

Hyperspectral change detection (CD) can be effectively performed using deep-learning networks. Although these approaches require qualified training samples, it is difficult to obtain ground-truth data in the real world. Preserving spatial information during training is difficult due to structural limitations. To solve such problems, our study proposed a novel CD method for hyperspectral images (HSIs), including sample generation and a deep-learning network, called the recurrent three-dimensional (3D) fully convolutional network (Re3FCN), which merged the advantages of a 3D fully convolutional network (FCN) and a convolutional long short-term memory (ConvLSTM). Principal component analysis (PCA) and the spectral correlation angle (SCA) were used to generate training samples with high probabilities of being changed or unchanged. The strategy assisted in training fewer samples of representative feature expression. The Re3FCN was mainly comprised of spectral–spatial and temporal modules. Particularly, a spectral–spatial module with a 3D convolutional layer extracts the spectral–spatial features from the HSIs simultaneously, whilst a temporal module with ConvLSTM records and analyzes the multi-temporal HSI change information. The study first proposed a simple and effective method to generate samples for network training. This method can be applied effectively to cases with no training samples. Re3FCN can perform end-to-end detection for binary and multiple changes. Moreover, Re3FCN can receive multi-temporal HSIs directly as input without learning the characteristics of multiple changes. Finally, the network could extract joint spectral–spatial–temporal features and it preserved the spatial structure during the learning process through the fully convolutional structure. This study was the first to use a 3D FCN and a ConvLSTM for the remote-sensing CD. To demonstrate the effectiveness of the proposed CD method, we performed binary and multi-class CD experiments. Results revealed that the Re3FCN outperformed the other conventional methods, such as change vector analysis, iteratively reweighted multivariate alteration detection, PCA-SCA, FCN, and the combination of 2D convolutional layers-fully connected LSTM.

Change Detection in Hyperspectral Images Using Recurrent 3D Fully Convolutional Networks

With advances in medicine and healthcare systems, the average life expectancy of human beings has increased to more than 80 yrs. As a result, the demographic old-age dependency ratio (people aged 65 or above relative to those aged 15–64) is expected to increase, by 2060, from ∼28% to ∼50% in the European Union and from ∼33% to ∼45% in Asia (Ageing Report European Economy, 2015). Therefore, the percentage of people who need additional care is also expected to increase. For instance, per studies conducted by the National Program for Health Care of the Elderly (NPHCE), elderly population in India will increase to 12% of the national population by 2025 with 8%–10% requiring utmost care. Geriatric healthcare has gained a lot of prominence in recent years, with specific focus on fall detection systems (FDSs) because of their impact on public lives. According to a World Health Organization report, the frequency of falls increases with increase in age and frailty. Older people living in nursing homes fall more often than those living in the community and 40% of them experience recurrent falls (World Health Organization, 2007). Machine learning (ML) has found its application in geriatric healthcare systems, especially in FDSs. In this paper, we examine the requirements of a typical FDS. Then we present a survey of the recent work in the area of fall detection systems, with focus on the application of machine learning. We also analyze the challenges in FDS systems based on the literature survey.

/pdf/a-survey-on-recent-advances-in-wearable-fall-detection-1kyu9lrve6.pdf

A Survey on Recent Advances in Wearable Fall Detection Systems

The risk of falls in older adults restrict their social life and independent living. The assisted living devices help older adults to live independently in their home, giving a psychological boost, and releasing the burden on the caregiver and the healthcare providers. A robust and accurate fall detection system is essential to provide immediate help and to reduce the severe post-fall consequences, and the associated medical care cost significantly. This review aims to provide a comprehensive technical insight into the existing fall detection system, to classify various approaches and the challenges encountered during implementation. The fall detectors are broadly classified into three categories, namely wearable, ambiance-based, and hybrid sensing detectors, which are further explored by the sensor technology. This review provides a comprehensive overview of each competing sensor technology ranging from an accelerometer, pressure sensor, and radar to camera-based and their infusion into a complete fall detection system. It outlines the strength and limitations of different sensor fall detection systems in terms of feature extraction, classification, performance, and experimental dataset. The user adaptability, installation complexity, and power requirement of the systems are the main areas, which are not addressed adequately in the literature. In the end, the review provides a basic framework in deciding the technology for a specific scenario or location according to the prerequisites for the deployment.

Sensor Technologies for Fall Detection Systems: A Review

Fall detection is an important public healthcare problem. Timely detection could enable instant delivery of medical service to the injured. A popular nonintrusive solution for fall detection is based on videos obtained through ambient camera, and the corresponding methods usually require a large dataset to train a classifier and are inclined to be influenced by the image quality. However, it is hard to collect fall data and instead simulated falls are recorded to construct the training dataset, which is restricted to limited quantity. To address these problems, a three-dimensional convolutional neural network (3-D CNN) based method for fall detection is developed, which only uses video kinematic data to train an automatic feature extractor and could circumvent the requirement for large fall dataset of deep learning solution. 2-D CNN could only encode spatial information, and the employed 3-D convolution could extract motion feature from temporal sequence, which is important for fall detection. To further locate the region of interest in each frame, a long short-term memory (LSTM) based spatial visual attention scheme is incorporated. Sports dataset Sports-1 M with no fall examples is employed to train the 3-D CNN, which is then combined with LSTM to train a classifier with fall dataset. Experiments have verified the proposed scheme on fall detection benchmark with high accuracy as 100%. Superior performance has also been obtained on other activity databases.

Deep Learning for Fall Detection: Three-Dimensional CNN Combined With LSTM on Video Kinematic Data

Fall detection is an important problem in the field of public health care, which is especially crucial for instant medical service delivery to the injured elderly due to falls. Ambient camera based fall detection has been a recognized non-intrusive and publicly acceptable method, where video data is employed to discriminate fall event from daily activities. Fall detection with videos usually requires a large dataset to extract features and train the classifier. However, it is hard to collect free-living environment fall data and instead simulated falls by young people have been collected to construct the training dataset, which is controlled intentional behavior and restricted to limited quantity of samples. In addition, the existing video based fall detection methods need segment the subject first, which is inclined to be influenced by image noise, illumination variation and occlusion. To address these problems, a three dimensional convolutional neural network (3D CNN) based method for fall detection is developed which only uses kinetic data to train an automatic feature extractor. Besides the spatial feature in 2D image, the motion information from the video could also be encoded by the three dimensional convolutions over the frames. A LSTM based spatial visual attention scheme is then incorporated, which could enable the network to focus on the key regions. Sports dataset Sports-1M with no fall examples is employed to train the 3D CNN and the visual attention model is trained on the small Multiple Cameras Fall Dataset. Then the visual attention based 3D CNN is employed to extract the features from the videos with fall event and implement fall detection. Experiments have shown the superior performance of the proposed scheme on fall dataset with high detection accuracy of 100%.

Visual guided deep learning scheme for fall detection

The ecological conservation and high-quality development of the Yellow River basin (YRB) has been adopted as a major national strategy of China. However, the YRB is still afflicted by floods. Here, we proposed a flood risk indicator using direct economic loss degree and improved the SNRD (station-based nonlinear regression downscaling model) and simulated extreme precipitation processes. The correlation coefficient of downscaled average extreme precipitation of CMORPH and CMIP6 data reached 0.817. Moreover, we evaluated flood risk and flood hazard across the YRB based on the sixth phase Coupled Model Intercomparison Project (CMIP6) data under different SSPs. Under SSP126, SSP245, and SSP585 scenarios, the areas with increasing flood hazards during 2015–2045 accounted for 65.2, 69.0, and 64.5% of the entire YRB. In the spatial pattern, flood hazards decreased from southeastern to northwestern parts of the YRB. When compared with the spatial pattern of flood risks in 2015, regions with high flood risks expanded slightly and regions with low flood risks shrunk slightly. Higher flood risks can be observed in the middle and lower YRB and particularly in the lower YRB. These findings are critical for the mitigation of flood risk across the YRB under warming climate.

Amplifying Flood Risk Across the Lower Yellow River Basin, China, Under Shared Socioeconomic Pathways

To solve the problems of the low energy efficiency and slow penetration rate of drilling, we took the geological data of adjacent wells, real-time logging data, and downhole engineering parameters as inputs; the mechanical specific energy and unit footage cost as multi-objective optimization functions; and the machine pump equipment limit as the constraint condition. A constrained Bayesian optimization algorithm model was established for the optimization solution, and drilling parameters such as weight-of-bit, revolutions per minute, and flowrate were optimized in real time. Through a comparison with NSGA-II, random search, and other optimization algorithms, and the application results of example wells, we show that the established Bayesian optimization algorithm has a good optimization effect while maintaining timeliness. It is suitable for real-time optimization of drilling parameters, can aid a driller in identifying the drilling rate and potential tapping area, and provides a decision-making basis for avoiding the low-efficiency rock-breaking working area and improving rock-breaking efficiency.

https://www.mdpi.com/1996-1073/15/21/8030/pdf?version=1668683543

Real-Time Drilling Parameter Optimization Model Based on the Constrained Bayesian Method

https://doi.org/10.1016/j.isci.2023.105930

Jinbo Song

Papers

Deep Learning for Fall Detection: Three-Dimensional CNN Combined With LSTM on Video Kinematic Data

Visual guided deep learning scheme for fall detection

Amplifying Flood Risk Across the Lower Yellow River Basin, China, Under Shared Socioeconomic Pathways

Real-Time Drilling Parameter Optimization Model Based on the Constrained Bayesian Method

Reverse subsidy dilemma caused by the transformation from individual heating to central heating